Video & Animation

Build a local AI "content operating system" for one business or many isolated businesses (an agency's clients). One Next.js engine plus one folder per business, with an owner-approved brand kit, an approve-before-generate idea store, a grounded trend radar, competitor tracking, HTML→PNG export, optional AI image/video/animation, a chat assistant with memory, owner-confirmed publishing, a CRM and an optional knowledge-vault graph. Every spawned AI agent is confined (no shell, no access to other businesses). Works with any coding agent (Claude Code, Codex, Cursor, Kimi…). It ALWAYS interviews first, starting with "one business or several isolated ones?", then builds. Use when someone wants a system to run their or their clients' content ("build me a content OS", "something like my friend's content OS", "a dashboard to run my content", "a system to run my clients' content", "an AI content OS for my agency"), even if they never say "content OS".

Makes and auto-publishes one free animated-text "facts / motivation" YouTube Short per day — picks a fresh topic, verifies every fact on the web, renders a 1080x1920 video with code (no AI credits), hosts it on GitHub and schedules it on YouTube through Metricool, alternating English and Urdu days. Use this whenever the user asks to make, post, upload or schedule today's YouTube Short, run the daily Shorts routine, manage the facts channel, or check how the Shorts are performing — even if they just say "aaj ki video bana do" or "YouTube wala kaam kar do".

Plan and build scroll-driven story page prototypes from scene copy, backgrounds, and video frame sequences using the Frameflow workbench. Use when someone wants editable desktop/mobile scenes, frame extraction, and timed transitions; do not treat it as a production website exporter.

Sovereign Google Calendar + Zoom Meeting scheduler skill. Checks real-time multi-calendar Google free/busy availability, provisions Zoom video meetings (Server-to-Server OAuth or PMI fallback), stages Google Calendar events with Human-in-the-Loop (HITL) email safety guardrails, and generates .ics / Google Calendar links.

生成扎提风格的 3 分钟中文男女关系/爱情影像随笔：素材可按客户要求随时替换（客户实拍、公版电影、AI 联网找的免费 stock、照片、纯文字、混合），雨伞/雨/胶片视觉脊柱、宋体动效、3:4 封面。Use when the user asks for a relationship/love essay video, a client-customized episode, or a new episode in the style of 《好人与错的人》.

CLAUDE BUSINESS GOD MODE hub. Use when someone wants to launch, onboard, grow or run a business with Claude end to end, or asks which God Mode to use. Ties together the Ultimate CRM Template (leads, quotes, jobs, invoices, payments, crew and client portals), Meta Ads God Mode (paid media, paused-first, approval-gated), SEO God Mode (audits, local SEO, Search Console, AI search) and Video Editing God Mode (reels, Shorts, ad creatives, client video approvals). Runs the shared business profile and the cross-component playbooks.

Generate images and videos from a prompt on an omg.dev Computer with omg_generate_image and omg_generate_video. Every call spends the user's omg credits. Use when the task needs a new picture, icon, illustration, or short clip, not for editing a file that already exists.

Design, revise, standardize, and insert figures for Chinese natural science fund proposals, especially technical route diagrams, research-content logic diagrams, data-flow diagrams, active-observation loops, evaluation charts, and research-background figures. Use when Codex must create or update SVG/PNG figures, synchronize figures with a Chinese grant proposal or DOCX, match the user's established fund-proposal visual style, or audit figure-text consistency, colors, typography, arrows, shadows, and Word captions.

Cut, caption and edit videos locally with the `wecut` CLI (FFmpeg on this machine, no cloud, no API key). Use when asked to make short-form clips, add captions or karaoke subtitles, trim or join videos, turn photos into a slideshow, add text, logos, music or transitions, render 9:16 / 1:1 / 16:9 video, analyse why a viral video works, or reuse its format as a template on new footage.

分析結果（グラフ画像・CSV/NPZ等のデータ・解析スクリプト・ノートブック）を、Nature系ジャーナルに採択されるレベルの多パネルFigure・Table・Captionにまとめるスキル。起動後に「どの結果を1枚のFigureにまとめるか」をユーザーに確認し、指示がなければ科学的ストーリー（What→How→Why→Performance→Impact）に沿って結果の取捨選択・パネル配置・配色まで自分で設計し、Arial 5–7 pt・89/183 mm幅・統一配色のベクターPDF/SVGを作ってQAまで行う。「結果を図にまとめて」「論文用のFigureを作って」「複数のグラフを1枚に」「Figure 1の概要図」「図を綺麗に/投稿用に整えて」「配色やフォントを統一」「Figure captionを書いて」「結果の表を作って」など、研究・分析結果を論文・投稿・発表用の図表に仕上げる依頼では、Natureと明示されていなくても必ずこのスキルを使うこと。Also use for any request in English for publication-quality, multi-panel or journal-ready figures from analysis results.

从主题或文稿制作中文讲解视频：联网核实并确认文案、声音形式与视觉风格，再用代码制作配乐字幕版或真人演说 API 配音版。适用于资讯、产品与技术讲解；不用于 AI 生成视频镜头。

Plan, create, revise, or deliver a video project from a brief, script, footage, images, or an existing edit. Use for narrative films, social videos, explainers, product videos, documentaries, motion graphics, and AI-generated video; route to the project's existing tools and review the actual rendered result. Do not use for general video-tool questions that do not ask to make or change a video.

用户问「我哪一期讲过 X」「这几部视频里谁说过 Y」「X 在我的视频里是怎么讲的」「有哪些讲 X 的视频」这类要在多部视频里找答案的问题时用：按意思检索、按视频去重、按当前版本重新定位，只凭找回来的原话回答，每条论断注明视频与时间，覆盖不全时说明。不用于总结或改写一部视频（那是总结、博客），也不改视频。

旁白、视频切片与文字动画混搭的成片：拿一条新闻、一件事、一段八卦、一个产品或人物的故事，从网上与用户的视频库里搜素材、切当事人的原声，配旁白剪成一条画面一直在动的片子，推文、引语、日期、数字做成压在画面上的卡片。题材不限；别的成片里要加一段这样的切片也用它。整段画面由代码画出来的讲解片走 explainer-video，剪已有的口播走 talking-head-cut。

Make a short, verified math / computer-vision / ML explainer video (computed animation + captions, optional translated version, narration script and TTS voice-over) with the animkit library in this repo. Use when the user asks for an explainer video, an animation of a concept / paper / mechanism, a storyboard for one, or a review / revision round of one.

>- Generate, export, or convert finished videos (or code-rendered videos) into native, self-contained JianYing Pro (剪映 / CapCut) project drafts, and automatically launch JianYing to open the project immediately with zero missing-media prompts. Use when the user wants to export a video, script, or timeline to JianYing, create a JianYing project from a video, or automate draft generation.

>- Write and lint the title and thumbnail for a YouTube video as one pairing, checking truncation, duplication and vagueness before publish. Use for "title ideas", "what should I call this", "thumbnail text", "my CTR is bad", packaging, or any request to rename or repackage an existing video.

用故事板规划并制作 HyperFrames 视频。适用于识别共享主体、选择连续形变方案、按依赖并行制作镜头、验收关键帧、拼接总时间线，以及处理镜头连续性问题。

Turn academic papers into learning videos by first producing a Chinese academic-style summary, then narration, visual planning, storyboards, and video review. Render videos when suitable tools are available. Use for paper-to-video learning summaries.

>- Turn a raw recording's transcript into an edit decision list - dead air, filler cues and retakes, with timecodes. Use for "edit this", "cut the dead space", "tighten this video", "I rambled", or any request to shorten footage from a transcript.

>- Write YouTube chapters from a transcript, validated against YouTube's own rules so they actually render. Use for "add chapters", "timestamps", "break this video into sections".

>- Audit a YouTube channel end to end - packaging, consistency, the first fifteen seconds, and what to fix first. Use for "audit my channel", "why isn't my channel growing", "review my videos", or a pasted channel URL.

Turn slides, a PDF deck, course notes or a webinar outline into a long-form narrated training/course video (10–60 min, 16:9) — script per slide, ElevenLabs narration with word timings (Prem / Indian-English voices), each slide built up part-by-part on spoken cues with an easing camera, push transitions, progress bar and chapter markers, ducked music bed, light SFX, YouTube chapters and lesson splits. Use when the user says "make a course video", "training video from this PDF/deck", "narrate these slides", "lesson/module video", or gives a deck and wants a long educational video ("normal editing, not heavy motion graphics").

End-to-end pipeline for editing Hinglish talking-head reels and product-ad reels (1080x1920, Instagram/Shorts) in the ~/video-editing studio — retake removal, tightened pauses, Roman karaoke captions, word-synced motion graphics, layered SFX, music bed, premium grade, -14 LUFS export. Use when the user gives talking-head/speech footage (your channel or any client), says "edit this reel", "new project from inbox", "make a product ad", or asks to re-render/tweak a version of an existing speech reel.